#Class 05: Data visualization 
# use ggplot2 package 
library(ggplot2) # load the package
head(cars)
##   speed dist
## 1     4    2
## 2     4   10
## 3     7    4
## 4     7   22
## 5     8   16
## 6     9   10
# all ggplots have at least 3 layers
#data + aes + geoms
ggplot(data = cars) + aes(x = speed, y = dist) +
  geom_point() +
  # geom_line() + 
   geom_smooth(method = "lm") +
  labs(title = "stopping dstance of old cars",
       x = "speed (MPH)",
       y = "stopping distance (ft)")
## `geom_smooth()` using formula 'y ~ x'

# ggplot is  nothe only graphic system
plot(cars$speed, cars$speed)

plot(cars)

url <- "https://bioboot.github.io/bimm143_S20/class-material/up_down_expression.txt"
genes <- read.delim(url)
head(genes)
##         Gene Condition1 Condition2      State
## 1      A4GNT -3.6808610 -3.4401355 unchanging
## 2       AAAS  4.5479580  4.3864126 unchanging
## 3      AASDH  3.7190695  3.4787276 unchanging
## 4       AATF  5.0784720  5.0151916 unchanging
## 5       AATK  0.4711421  0.5598642 unchanging
## 6 AB015752.4 -3.6808610 -3.5921390 unchanging
nrow(genes)
## [1] 5196
# how many genes are up?
table(genes$State)
## 
##       down unchanging         up 
##         72       4997        127
#what percentage of the genes are up?
# round() round up to whole number or certain digits
round(table(genes$State)/nrow(genes) *100, 3)
## 
##       down unchanging         up 
##      1.386     96.170      2.444
# make a figure
p <- ggplot(genes) + aes(x=Condition1, y=Condition2, col = State) +
  geom_point()
p

#change the color
p + scale_color_manual(values = c("blue", "grey", "red")) 

# bad color
p+ geom_point(col = "blue")

# nicer color
p + aes(color = State)

# explor the gapminder dataset
# install.packages("gapminder")
library(gapminder)
head(gapminder)
## # A tibble: 6 × 6
##   country     continent  year lifeExp      pop gdpPercap
##   <fct>       <fct>     <int>   <dbl>    <int>     <dbl>
## 1 Afghanistan Asia       1952    28.8  8425333      779.
## 2 Afghanistan Asia       1957    30.3  9240934      821.
## 3 Afghanistan Asia       1962    32.0 10267083      853.
## 4 Afghanistan Asia       1967    34.0 11537966      836.
## 5 Afghanistan Asia       1972    36.1 13079460      740.
## 6 Afghanistan Asia       1977    38.4 14880372      786.
ggplot(gapminder, 
       aes(year, lifeExp, col = continent)) + 
  #geom_point(alpha = 0.4)+
  geom_jitter(width = 0.3, alpha = 0.4) +
  #geom_boxplot(alpha = 0.3, aes(group = year))
  geom_violin(aes( group = year),alpha = 0.2, draw_quantiles = 0.5)

# install the plotly
# install.packages("plotly")
# interactive plot
library(plotly)
## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout
ggplotly()